A Hierarchical Demand Response Framework for Data Center Power Cost Optimization under Real-World Electricity Pricing
A Hierarchical Demand Response Framework for Data Center Power Cost Optimization under Real-World Electricity Pricing
复制标题
DOI：
10.1109/mascots.2014.45
复制
发表时间：
2014-09
期刊：
影响因子：
--
通讯作者：
Cheng Wang;B. Urgaonkar;Qian Wang;G. Kesidis
中科院分区：
文献类型：
--
作者：
Cheng Wang;B. Urgaonkar;Qian Wang;G. Kesidis
我们研究了在工作负载和实际定价方案不确定的情况下优化数据中心电费的问题。我们的重点是使用控制旋钮来调节IT设备的功耗。为了克服投射/更新这样的控制问题的困难和它们通常遭受的计算棘手性，我们提出并评估了一种分层优化框架，其中上层使用（i）时间聚合来将计费周期期间的决策时刻的数量限制为计算上可行的值，以及（ii）空间（即，控制旋钮）聚集，由此它利用标记为需求丢弃和需求延迟的两个抽象旋钮来对功率控制旋钮的大而多样的集合进行建模。这些抽象的旋钮根据流体动力需求进行操作。我们的建模背后的关键见解是，大多数IT控制旋钮的功率调制效果可以被简洁地捕获为降低和/或延迟一部分功率需求。这些决策被传递到一个较低的层，该层利用现有的研究将它们转化为真实的IT旋钮的决策。我们为上层开发了一套算法，用于处理不同形式的输入不确定性。所提出的方法的实验评估提供了有希望的结果：例如，它为流媒体服务器和基于MapReduce的批处理工作负载分别提供了大约25%和18%的净成本节省。
We study the problem of optimizing data center electric utility bill under uncertainty in workloads and real-world pricing schemes. Our focus is on using control knobs that modulate the power consumption of IT equipment. To overcome the difficulty of casting/updating such control problems and the computational intractability they suffer from in general, we propose and evaluate a hierarchical optimization framework wherein an upper layer uses (i) temporal aggregation to restrict the number of decision instants during a billing cycle to computationally feasible values, and (ii) spatial (i.e., control knob) aggregation whereby it models the large and diverse set of power control knobs with two abstract knobs labeled demand dropping and demand delaying. These abstract knobs operate upon a fluid power demand. The key insight underlying our modeling is that the power modulation effects of most IT control knobs can be succinctly captured as dropping and/or delaying a portion of the power demand. These decisions are passed onto a lower layer that leverages existing research to translate them into decisions for real IT knobs. We develop a suite of algorithms for our upper layer that deal with different forms of input uncertainty. An experimental evaluation of the proposed approach offers promising results: e.g., it offers net cost savings of about 25% and 18% to a streaming media server and a MapReduce-based batch workload, respectively.